Summary of Night — Non-line-of-sight Imaging From Indirect Time Of Flight Data, by Matteo Caligiuri et al.
NIGHT – Non-Line-of-Sight Imaging from Indirect Time of Flight Data
by Matteo Caligiuri, Adriano Simonetto, Pietro Zanuttigh
First submitted to arxiv on: 28 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach to acquiring objects outside the Line-of-Sight (LOS) of cameras using an off-the-shelf indirect Time of Flight sensor. By introducing a Deep Learning model that reframes surfaces as virtual mirrors, the task becomes easier to handle and annotated training data can be constructed. This allows for the retrieval of depth information from the hidden scene. The paper also provides a synthetic dataset for this task and demonstrates its feasibility. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a way to see objects outside what cameras can normally see using a regular camera that takes time-of-flight measurements. They used a special computer model that treats surfaces as mirrors, making it easier to create training data and get depth information from hidden scenes. This is the first time this has been done without any special equipment. |
Keywords
» Artificial intelligence » Deep learning
